Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Guang-Tong Zhou"'
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2010 (2010)
A critical step in an automatic fingerprint recognition system is the segmentation of fingerprint images. Existing methods are usually designed to segment fingerprint images originated from a certain sensor. Thus their performances are significantly
Externí odkaz:
https://doaj.org/article/6660f0f44fa241c3bd3380028609912a
Autor:
Guang-Tong Zhou, Yu-Hu Mu, Yuan-Wen Song, Zhuang-Fei Zhang, Yue-Wen Zhang, Wei-Xia Shen, Qian-Qian Wang, Biao Wan, Chao Fang, Liang-Chao Chen, Ya-Dong Li, Xiao-Peng Jia
Publikováno v:
Chinese Physics B. 31:068103
The synergistic influences of boron, oxygen, and titanium on growing large single-crystal diamonds are studied using different concentrations of B2O3 in a solvent–carbon system under 5.5 GPa–5.7 GPa and 1300 °C–1500 °C. It is found that the b
Visual data such as images and videos contain a rich source of structured semantic labels as well as a wide range of interacting components. Visual content could be assigned with fine-grained labels describing major components, coarse-grained labels
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a69a5778a3a09c7e7bc9ce274e2129a3
http://arxiv.org/abs/1802.06459
http://arxiv.org/abs/1802.06459
Publikováno v:
Machine Learning. 90:127-160
This paper introduces mass estimation--a base modelling mechanism that can be employed to solve various tasks in machine learning. We present the theoretical basis of mass and efficient methods to estimate mass. We show that mass estimation solves pr
Publikováno v:
Pattern Recognition. 45:1707-1720
This paper presents a novel ranking framework for content-based multimedia information retrieval (CBMIR). The framework introduces relevance features and a new ranking scheme. Each relevance feature measures the relevance of an instance with respect
Publikováno v:
CVPR
Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels that depi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3724fb25711e45affd7ed088f15fb88b
http://arxiv.org/abs/1511.05616
http://arxiv.org/abs/1511.05616
Autor:
Arash Vahdat, Stephen Se, Greg Mori, Mehran Khodabandeh, Mehrsan Javan Roshtkhari, Guang-Tong Zhou, Hossein Hajimirsadeghi
Publikováno v:
CVPR Workshops
We present a novel approach for discovering human interactions in videos. Activity understanding techniques usually require a large number of labeled examples, which are not available in many practical cases. Here, we focus on recovering semantically
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33f64722b625f0c0201299215bf3378d
http://arxiv.org/abs/1502.03851
http://arxiv.org/abs/1502.03851
Publikováno v:
Computer Vision-ECCV 2014 Workshops ISBN: 9783319161983
ECCV Workshops (3)
ECCV Workshops (3)
Human action categories exhibit significant intra-class variation. Changes in viewpoint, human appearance, and the temporal evolution of an action confound recognition algorithms. In order to address this, we present an approach to discover action pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b9c1d761cd49fdd946b5e241dd370af
https://doi.org/10.1007/978-3-319-16199-0_7
https://doi.org/10.1007/978-3-319-16199-0_7
Publikováno v:
Computer Vision – ECCV 2014 ISBN: 9783319105987
ECCV (6)
ECCV (6)
We present an algorithm for automatically clustering tagged videos. Collections of tagged videos are commonplace, however, it is not trivial to discover video clusters therein. Direct methods that operate on visual features ignore the regularly avail
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a94b874a0dd97b4f351c779ddcc61b99
https://doi.org/10.1007/978-3-319-10599-4_34
https://doi.org/10.1007/978-3-319-10599-4_34
Publikováno v:
CVPR
We conduct image classification by learning a class-to-image distance function that matches objects. The set of objects in training images for an image class are treated as a collage. When presented with a test image, the best matching between this c